© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 32519
    Prev
    Next
    INDEX
    Explanations

    ages and above

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ºæľŁ
    -0.10
    ION
    -0.09
    åĵ¥ä»¬
    -0.09
    åı«å£°
    -0.08
    ä¸Ń举
    -0.08
    amos
    -0.08
    æŃ¥æŃ¥
    -0.08
    2
    -0.08
    1
    -0.08
    注æĺİ
    -0.08
    POSITIVE LOGITS
    顶
    0.10
    åģľæĶ¾
    0.09
    /english
    0.09
     поиÑģк
    0.08
    æ¯ħ
    0.08
    (inner
    0.08
    (age
    0.08
    aga
    0.08
    stra
    0.08
    /legal
    0.08
    Activations Density 0.078%

    No Known Activations